© 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. 51811
    Prev
    Next
    INDEX
    Explanations

    ^

    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
    ffaa
    -0.09
    -grown
    -0.08
     isot
    -0.08
     nare
    -0.08
     amb
    -0.07
    ântico
    -0.07
    Growing
    -0.07
     میشود
    -0.07
    ilməsi
    -0.07
    err
    -0.07
    POSITIVE LOGITS
    тас
    0.09
    炮
    0.08
     Jeśli
    0.08
    道路
    0.08
    atura
    0.07
     Laden
    0.07
     ADC
    0.07
     adherence
    0.07
     Nếu
    0.07
    ­ta
    0.07
    Activations Density 0.000%

    No Known Activations