Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90085
    Prev
    Next
    INDEX
    Explanations

    537

    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
     regrett
    -0.09
    :absolute
    -0.09
     psychiatric
    -0.08
    ाँ
    -0.08
     remettre
    -0.08
     Theology
    -0.07
     mural
    -0.07
     ছাড়
    -0.07
     takeaway
    -0.07
    føre
    -0.07
    POSITIVE LOGITS
     sie
    0.08
    -MM
    0.08
    734
    0.08
     الاق
    0.07
    8
    0.07
    728
    0.07
     Sen
    0.07
    _OB
    0.07
     Beob
    0.07
     observations
    0.07
    Activations Density 0.000%

    No Known Activations