© 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. 19-RESID-POST-AA
    11. 18430
    Prev
    Next
    INDEX
    Explanations

    almost

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Various
    -0.08
     Only
    -0.07
     यदि
    -0.07
     MUST
    -0.07
    ONLY
    -0.07
     Created
    -0.07
    跃
    -0.07
     Fet
    -0.07
     абсолютно
    -0.07
    ANY
    -0.07
    POSITIVE LOGITS
     but
    0.19
    -but
    0.16
    but
    0.15
     mutta
    0.13
     কিন্তু
    0.13
     पण
    0.13
     pero
    0.13
    But
    0.13
    ,but
    0.12
    ，但
    0.12
    Activations Density 0.009%

    No Known Activations