© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 48065
    Prev
    Next
    INDEX
    Explanations

    -free

    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
     rushed
    -0.08
     Gl
    -0.08
     MATCH
    -0.07
     burdens
    -0.07
    ात्मक
    -0.07
    银
    -0.07
    Gl
    -0.07
     Maintain
    -0.07
     hinted
    -0.07
    विश्व
    -0.07
    POSITIVE LOGITS
     divisor
    0.08
    rectangle
    0.08
     المشاكل
    0.07
     rectangle
    0.07
     vlak
    0.07
    Sequences
    0.07
     odd
    0.07
    okoj
    0.07
    uest
    0.07
     khỏi
    0.07
    Activations Density 0.001%

    No Known Activations