© 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. 50894
    Prev
    Next
    INDEX
    Explanations

    п

    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
    olicies
    -0.09
    olic
    -0.08
     سياسية
    -0.08
    omeza
    -0.08
    ాల
    -0.08
     politik
    -0.08
    ాలు
    -0.08
    ాల్
    -0.08
    ignée
    -0.08
    ਿੰ
    -0.08
    POSITIVE LOGITS
    ಿಕ
    0.09
    ar
    0.09
    _ar
    0.09
    ars
    0.09
    arz
    0.09
    yección
    0.08
    િક
    0.08
    ಿಕ್ಕ
    0.08
    (ar
    0.08
    icken
    0.08
    Activations Density 0.016%

    No Known Activations