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. 102880
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Crisp
    -0.08
    ’
    -0.08
    ’.
    -0.07
     Merit
    -0.07
    ’l
    -0.07
    .Getter
    -0.07
     Cerv
    -0.07
    -0.07
     domic
    -0.07
     protég
    -0.07
    POSITIVE LOGITS
    (三
    0.09
    -three
    0.09
     ત્રણ
    0.08
    _three
    0.08
    minecraft
    0.08
    rd
    0.08
     三
    0.08
     delitos
    0.08
    250
    0.08
     franz
    0.08
    Activations Density 0.152%

    No Known Activations