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. 112954
    Prev
    Next
    INDEX
    Explanations

    her

    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
     Eurovision
    -0.10
     তা
    -0.08
    abolism
    -0.08
     introdu
    -0.08
     Europeo
    -0.08
    strncmp
    -0.08
    abolic
    -0.08
    strlen
    -0.07
     exactamente
    -0.07
     exactement
    -0.07
    POSITIVE LOGITS
     χω
    0.08
     ஆகிய
    0.08
     nasal
    0.07
    タ
    0.07
    Research
    0.07
    ブラ
    0.07
    ייג
    0.07
     nage
    0.07
     kız
    0.07
    .mar
    0.07
    Activations Density 0.003%

    No Known Activations