© 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. 78796
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    457
    -0.08
    (?)
    -0.07
     (↵↵
    -0.07
     funky
    -0.07
    Runtime
    -0.07
     studs
    -0.07
     numerator
    -0.07
     calientes
    -0.07
     jugadores
    -0.07
    วน
    -0.07
    POSITIVE LOGITS
     genuinely
    0.13
     honestly
    0.11
     своев
    0.11
     promptly
    0.11
     sincerely
    0.11
     sincere
    0.10
    诚信
    0.10
     尊
    0.09
     willingly
    0.09
     honn
    0.09
    Activations Density 0.053%

    No Known Activations