Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43887
    Prev
    Next
    INDEX
    Explanations

    and

    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
    .filters
    -0.08
    Accumulator
    -0.08
    ighters
    -0.08
    ?↵↵↵
    -0.08
    611
    -0.07
    šla
    -0.07
    ARP
    -0.07
    proc
    -0.07
    650
    -0.07
    ↵↵
    -0.07
    POSITIVE LOGITS
     mus
    0.09
     muted
    0.08
     Jacobs
    0.07
    ႏွ
    0.07
     דע
    0.07
     ႏွ
    0.07
     NAB
    0.07
     နှ
    0.07
     oste
    0.07
     bone
    0.07
    Activations Density 0.056%

    No Known Activations