© 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. 50850
    Prev
    Next
    INDEX
    Explanations

    it

    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
     kwaad
    -0.09
     længere
    -0.08
     Extensive
    -0.08
     rigidity
    -0.08
    ibilidade
    -0.08
     umfang
    -0.08
     completeness
    -0.08
     Derecho
    -0.08
     incurs
    -0.08
     Exhaust
    -0.08
    POSITIVE LOGITS
     tasteful
    0.15
     respectful
    0.15
     appropriate
    0.15
     PG
    0.14
    PG
    0.14
     subdued
    0.13
     classy
    0.13
     restrained
    0.13
     tame
    0.13
     toned
    0.13
    Activations Density 0.062%

    No Known Activations