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. 55555
    Prev
    Next
    INDEX
    Explanations

    PII / Personally Identifiable Info

    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
    授
    -0.08
     steht
    -0.08
    standing
    -0.08
    úna
    -0.08
     piling
    -0.08
     miš
    -0.07
     dwa
    -0.07
     dua
    -0.07
    965
    -0.07
     står
    -0.07
    POSITIVE LOGITS
    iod
    0.08
    iction
    0.08
    .app
    0.08
     Borough
    0.08
    __(↵
    0.08
    icts
    0.08
     transcripts
    0.08
    itev
    0.07
    __('
    0.07
    itized
    0.07
    Activations Density 0.001%

    No Known Activations