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. 24381
    Prev
    Next
    INDEX
    Explanations

    note

    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
     south
    -0.08
     పల
    -0.08
     snee
    -0.07
    atinum
    -0.07
    500
    -0.07
     million
    -0.07
    }/${
    -0.07
    ocre
    -0.07
     لأي
    -0.07
    想
    -0.07
    POSITIVE LOGITS
     linen
    0.08
     subscribe
    0.08
    pull
    0.08
    Subscribed
    0.08
    Bible
    0.08
     alty
    0.08
     transcripts
    0.08
     Beautiful
    0.08
    subscribe
    0.08
     akt
    0.07
    Activations Density 0.010%

    No Known Activations