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. 112026
    Prev
    Next
    INDEX
    Explanations

    area

    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
     underserved
    -0.09
    _bias
    -0.07
     मिलेगा
    -0.07
     biases
    -0.07
    uffed
    -0.07
    ിലുള്ള
    -0.07
    ens
    -0.07
     bias
    -0.07
    ือน
    -0.07
     Nazi
    -0.07
    POSITIVE LOGITS
     공식
    0.08
     Exemple
    0.08
    ork
    0.08
     formula
    0.08
     Trip
    0.08
     trin
    0.07
     আবেদন
    0.07
    Trip
    0.07
    Orb
    0.07
    ulugan
    0.07
    Activations Density 0.021%

    No Known Activations