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. 53868
    Prev
    Next
    INDEX
    Explanations

    Math problems and conditions

    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
    .labels
    -0.08
    ass
    -0.08
     professionally
    -0.07
     etiqu
    -0.07
     deadlines
    -0.07
     briefs
    -0.07
     Stellen
    -0.07
    ਆ
    -0.07
     ਵਿਚ
    -0.07
    annah
    -0.07
    POSITIVE LOGITS
     kugeza
    0.09
     varsa
    0.09
     isempty
    0.08
     мән
    0.08
     yür
    0.08
     houver
    0.08
     term
    0.08
     izraz
    0.07
    _term
    0.07
     Invitation
    0.07
    Activations Density 0.029%

    No Known Activations