© 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. 54807
    Prev
    Next
    INDEX
    Explanations

    occurrences over time

    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
    ARRIER
    -0.08
     chunky
    -0.08
     clarify
    -0.08
    _ZERO
    -0.08
    imismo
    -0.08
    acher
    -0.07
     HA
    -0.07
    chunk
    -0.07
     Schools
    -0.07
    icit
    -0.07
    POSITIVE LOGITS
     irgendwo
    0.09
    /all
    0.09
    Кат
    0.09
     கிட
    0.09
     algun
    0.08
    Representation
    0.08
     pernah
    0.08
    至少
    0.08
     είτε
    0.08
     algún
    0.08
    Activations Density 0.025%

    No Known Activations