© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51239
    Prev
    Next
    INDEX
    Explanations

    International agreements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kegiatan
    -0.08
    ashboard
    -0.08
     Prozesse
    -0.08
     SOP
    -0.08
     Activity
    -0.07
     NI
    -0.07
     Authority
    -0.07
     Authorities
    -0.07
     Bauch
    -0.07
     Procedures
    -0.07
    POSITIVE LOGITS
     recognition
    0.14
     recognize
    0.13
     recognizing
    0.13
     guarantees
    0.12
     tribute
    0.12
     reconnaître
    0.12
    Recognition
    0.12
     recognizes
    0.12
     loans
    0.12
     tribut
    0.12
    Activations Density 0.033%

    No Known Activations