© 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. 49637
    Prev
    Next
    INDEX
    Explanations

    Anime

    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
    3
    -0.07
    Kb
    -0.07
    12
    -0.07
    (PATH
    -0.07
    -P
    -0.07
    十三
    -0.07
     ત્રણ
    -0.07
    _P
    -0.07
    grand
    -0.07
     grand
    -0.07
    POSITIVE LOGITS
     taget
    0.09
     nhiệm
    0.09
    rụ
    0.08
     अभिनय
    0.08
     contar
    0.08
     الروا
    0.08
    िविध
    0.08
     pux
    0.08
     weave
    0.08
    луу
    0.08
    Activations Density 0.001%

    No Known Activations