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. 111979
    Prev
    Next
    INDEX
    Explanations

    modal verbs

    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
     ગુણ
    -0.08
    力度
    -0.08
    वाही
    -0.08
     nhằm
    -0.08
     dauern
    -0.08
    /comments
    -0.08
     enviados
    -0.07
    旨
    -0.07
     borders
    -0.07
     климат
    -0.07
    POSITIVE LOGITS
    佩
    0.10
     തന്റെ
    0.09
     acqu
    0.09
    遇
    0.09
    Facing
    0.09
    .obtain
    0.09
    에게
    0.09
     obtains
    0.08
     தனது
    0.08
    受到
    0.08
    Activations Density 0.175%

    No Known Activations