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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1877
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    课
    -0.08
     થી
    -0.07
     во
    -0.07
    sto
    -0.07
    .tint
    -0.07
    01
    -0.07
     DFA
    -0.07
    ាក
    -0.07
     vivid
    -0.07
     occupational
    -0.07
    POSITIVE LOGITS
    도를
    0.08
     확보
    0.08
    олага
    0.08
     평균
    0.08
     로
    0.08
    도의
    0.08
    ाजा
    0.07
     투
    0.07
    flush
    0.07
     bestimmt
    0.07
    Activations Density 0.001%

    No Known Activations