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. 58860
    Prev
    Next
    INDEX
    Explanations

    Code, math, special characters

    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
    (pop
    -0.08
     avi
    -0.07
     Zit
    -0.07
     antiv
    -0.07
     celebrity
    -0.07
    agi
    -0.07
    _trans
    -0.07
     Té
    -0.06
     Apple's
    -0.06
    avi
    -0.06
    POSITIVE LOGITS
     naman
    0.10
    226
    0.09
    Bass
    0.09
     bass
    0.08
     pouvais
    0.08
     baja
    0.08
     Bass
    0.08
    bass
    0.07
     surcharge
    0.07
    orea
    0.07
    Activations Density 0.222%

    No Known Activations