© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30149
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
     पॉ
    -0.09
     estimated
    -0.09
    estimated
    -0.09
    pellier
    -0.08
     usize
    -0.08
     soins
    -0.08
     ukuya
    -0.08
     تقد
    -0.08
     runway
    -0.08
     surpassed
    -0.08
    POSITIVE LOGITS
    .compile
    0.09
     постоянно
    0.09
    .tokens
    0.08
     constants
    0.08
    Tokens
    0.08
    _constants
    0.08
    Expression
    0.08
     Leib
    0.08
    Constant
    0.08
    .Constant
    0.08
    Activations Density 0.058%

    No Known Activations