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. 54137
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    'altra
    -0.07
    _ids
    -0.07
    宠
    -0.07
     ™
    -0.07
    જૂ
    -0.07
    .ids
    -0.07
    Andere
    -0.07
    Outra
    -0.07
     heerlijke
    -0.07
    Javascript
    -0.07
    POSITIVE LOGITS
     celui
    0.09
     Leitung
    0.09
    撃
    0.08
     Stripe
    0.07
     Sammy
    0.07
     panne
    0.07
     ocasião
    0.07
     باس
    0.07
     TNT
    0.07
     einzelnen
    0.07
    Activations Density 0.095%

    No Known Activations