© 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 EvalsExportsAPI 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. 49907
    Prev
    Next
    INDEX
    Explanations

    .Is

    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
     Departure
    -0.08
     çalışma
    -0.08
    .fetchone
    -0.08
     Thickness
    -0.08
    departure
    -0.08
     Lightning
    -0.08
     ASAP
    -0.08
     MCU
    -0.07
     Walter
    -0.07
     thickness
    -0.07
    POSITIVE LOGITS
    Null
    0.18
    _null
    0.13
     Null
    0.12
    .null
    0.11
     null
    0.11
    -null
    0.10
    nul
    0.10
    Intern
    0.09
     nul
    0.09
    II
    0.09
    Activations Density 0.000%

    No Known Activations