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. 106166
    Prev
    Next
    INDEX
    Explanations

    learning technology research

    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
     man's
    -0.09
    Basically
    -0.09
     Ultras
    -0.09
     молит
    -0.09
    ուտբոլ
    -0.08
     иттипақ
    -0.08
     игә
    -0.08
    typeorm
    -0.08
    �का
    -0.08
     ئۆ
    -0.08
    POSITIVE LOGITS
     letter
    0.08
     observable
    0.07
     }];↵
    0.07
     alphabet
    0.07
     buffer
    0.07
     designated
    0.07
     represent
    0.07
    0.07
     descr
    0.07
     granular
    0.07
    Activations Density 0.000%

    No Known Activations