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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 48139
    Prev
    Next
    INDEX
    Explanations

    Code comments/potential bugs

    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
     unmistak
    -0.09
     dozens
    -0.09
     consequential
    -0.08
     zest
    -0.08
     mathem
    -0.08
     ensuing
    -0.08
     निम
    -0.08
     who've
    -0.07
     situated
    -0.07
     unten
    -0.07
    POSITIVE LOGITS
     presumably
    0.12
     incorrectly
    0.10
     wrongly
    0.09
    ,但是
    0.09
    ??
    0.09
     supposedly
    0.09
     (?)
    0.08
    Youtube
    0.08
     apparently
    0.08
     inside
    0.08
    Activations Density 0.080%

    No Known Activations