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. 78351
    Prev
    Next
    INDEX
    Explanations

    suppressors/silencers

    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
     distribute
    -0.08
     subset
    -0.08
    .prepare
    -0.07
    .drop
    -0.07
     win
    -0.07
     rally
    -0.07
     excellent
    -0.07
     relentless
    -0.07
     dear
    -0.07
    .indices
    -0.07
    POSITIVE LOGITS
    -equipped
    0.10
     tucked
    0.09
     attached
    0.09
     hooked
    0.09
    Attached
    0.09
    idepress
    0.08
     perched
    0.08
     Attached
    0.08
    ителем
    0.08
     tops
    0.08
    Activations Density 0.010%

    No Known Activations