© 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. 11-RESID-POST-AA
    11. 114211
    Prev
    Next
    INDEX
    Explanations

    elta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tobac
    -0.09
     Shut
    -0.08
     Outdoor
    -0.08
    (sockfd
    -0.08
    нать
    -0.08
     USP
    -0.08
     frying
    -0.08
     thị
    -0.08
     خشک
    -0.08
     шумо
    -0.08
    POSITIVE LOGITS
    .timedelta
    0.13
    duration
    0.11
     timedelta
    0.11
    .duration
    0.11
    (hours
    0.11
    Duration
    0.10
     duration
    0.10
    (Duration
    0.10
    -duration
    0.10
     durations
    0.10
    Activations Density 0.002%

    No Known Activations