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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130747
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     storyline
    -0.08
    stown
    -0.08
    _rpc
    -0.08
     superficial
    -0.08
    inia
    -0.08
     кора
    -0.08
    iiv
    -0.08
    _rs
    -0.07
     RPC
    -0.07
    omin
    -0.07
    POSITIVE LOGITS
    озе
    0.08
    äte
    0.08
     அண
    0.08
    BQ
    0.08
     atom
    0.08
     ventes
    0.07
     અથ
    0.07
     html
    0.07
     gedrag
    0.07
    YSICAL
    0.07
    Activations Density 0.003%

    No Known Activations