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. 111961
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ಣೆ
    -0.08
     gồm
    -0.08
    quences
    -0.07
    章节
    -0.07
    您好
    -0.07
    .neo
    -0.07
    .Sequence
    -0.07
     vorbereitet
    -0.07
     consequências
    -0.07
    iseer
    -0.07
    POSITIVE LOGITS
    лык
    0.08
     cush
    0.08
     alerg
    0.08
    shirt
    0.08
    bash
    0.07
    -edge
    0.07
     dod
    0.07
     dashed
    0.07
    oids
    0.07
    _alt
    0.07
    Activations Density 0.001%

    No Known Activations