© 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. 65478
    Prev
    Next
    INDEX
    Explanations

    crossword clues

    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
    ગ્રી
    -0.09
    velopp
    -0.08
     granular
    -0.08
     glycol
    -0.07
     infrastructure
    -0.07
     zone
    -0.07
    (glm
    -0.07
     GD
    -0.07
    ifecycle
    -0.07
    verl
    -0.07
    POSITIVE LOGITS
     cues
    0.10
     clues
    0.10
    提示
    0.09
     synonyms
    0.09
     clue
    0.09
    标题
    0.09
     prompts
    0.09
     Styles
    0.08
    编号
    0.08
     pistas
    0.08
    Activations Density 0.005%

    No Known Activations