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. 59638
    Prev
    Next
    INDEX
    Explanations

    git commands

    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
     linguistic
    -0.09
     handic
    -0.08
     measurable
    -0.08
     تقديم
    -0.08
     Ministry
    -0.08
    ©
    -0.07
    hashed
    -0.07
     crafts
    -0.07
     apresentado
    -0.07
    aud
    -0.07
    POSITIVE LOGITS
     git
    0.11
    Rollback
    0.11
    rollback
    0.09
    git
    0.09
     rollback
    0.09
    _merge
    0.09
    stash
    0.09
     inplace
    0.09
    _git
    0.09
    .git
    0.08
    Activations Density 0.006%

    No Known Activations