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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 106024
    Prev
    Next
    INDEX
    Explanations

    ratios and counting

    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
     radical
    -0.08
     BS
    -0.07
    тардың
    -0.07
     radicals
    -0.07
     radically
    -0.07
    -0.07
     직
    -0.07
     spiritual
    -0.07
    /fs
    -0.07
     seekers
    -0.07
    POSITIVE LOGITS
     overige
    0.08
     übr
    0.08
     annað
    0.08
     außerdem
    0.08
     `'
    0.08
    _only
    0.08
     Suppose
    0.08
     blant
    0.08
     ಸಮಸ್ಯ
    0.08
     statement
    0.07
    Activations Density 0.104%

    No Known Activations