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. 15-RESID-POST-AA
    6. 18949
    Prev
    Next
    INDEX
    Explanations

    coding errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    though
    -0.08
     mistake
    -0.08
     округ
    -0.08
     remorse
    -0.08
     approach
    -0.08
     incor
    -0.08
     rounding
    -0.08
    rounded
    -0.08
     answer
    -0.08
    उत्तर
    -0.08
    POSITIVE LOGITS
    .id
    0.15
    .get
    0.14
    .name
    0.14
    .to
    0.13
    .hash
    0.13
    .data
    0.13
    .
    0.13
    .key
    0.13
    .as
    0.12
    .nombre
    0.12
    Activations Density 0.011%

    No Known Activations