© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31031
    Prev
    Next
    INDEX
    Explanations

    as

    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
    ersen
    -0.09
    -0.08
     эффективности
    -0.08
     doute
    -0.08
    .RUNTIME
    -0.08
     meanwhile
    -0.08
     intrigu
    -0.07
     entanto
    -0.07
     doubt
    -0.07
     เข
    -0.07
    POSITIVE LOGITS
     combinación
    0.08
     Combination
    0.08
     combinação
    0.08
     mixture
    0.07
     Kron
    0.07
    opping
    0.07
     {\
    0.07
     Kombination
    0.07
     \"
    0.07
     последователь
    0.07
    Activations Density 0.052%

    No Known Activations