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. 120388
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     naro
    -0.09
    ावट
    -0.08
     touches
    -0.07
    -bodied
    -0.07
    ட
    -0.07
     stuff
    -0.07
    బ్బ
    -0.07
    हा
    -0.07
    Hamb
    -0.07
     poč
    -0.07
    POSITIVE LOGITS
     geworden
    0.09
    ೋಗ್ಯ
    0.09
    kick
    0.09
     varten
    0.09
    이며
    0.09
     bagi
    0.08
     בפני
    0.08
    .integer
    0.08
    ,也是
    0.08
    ombie
    0.07
    Activations Density 0.161%

    No Known Activations