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. 11-RESID-POST-AA
    6. 102591
    Prev
    Next
    INDEX
    Explanations

    perform

    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
     enr
    -0.09
    workers
    -0.08
    revision
    -0.08
    worthiness
    -0.08
    148
    -0.08
    kou
    -0.08
    kai
    -0.07
     guerr
    -0.07
    iseur
    -0.07
    kọ
    -0.07
    POSITIVE LOGITS
     Ov
    0.09
     الب
    0.08
    员
    0.08
    맨
    0.08
    Ov
    0.08
    驶
    0.07
     работы
    0.07
    -sch
    0.07
     aliquam
    0.07
    -songwriter
    0.07
    Activations Density 0.019%

    No Known Activations