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. 29977
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning

    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
    缓
    -0.09
    _RADIUS
    -0.09
    -radius
    -0.08
     pot
    -0.08
    _adc
    -0.08
    GRE
    -0.08
     abras
    -0.08
     tane
    -0.08
    診
    -0.08
    thood
    -0.07
    POSITIVE LOGITS
     count
    0.12
     factorial
    0.10
    count
    0.10
     counted
    0.10
    ,count
    0.10
     Count
    0.09
    .count
    0.09
    Count
    0.09
     permutations
    0.09
    .Count
    0.08
    Activations Density 0.022%

    No Known Activations