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. 53149
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    grader
    -0.08
    GPS
    -0.08
    ಂದ
    -0.08
     Distinguished
    -0.08
    .flatten
    -0.08
    .dist
    -0.08
    інің
    -0.08
    aka
    -0.08
     aboard
    -0.08
    сет
    -0.07
    POSITIVE LOGITS
     parentheses
    0.09
    钱
    0.08
     sh
    0.08
    整个
    0.08
     arithmetic
    0.07
     RHS
    0.07
     পুরো
    0.07
     multiplic
    0.07
     آخ
    0.07
     entire
    0.07
    Activations Density 0.018%

    No Known Activations