© 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. 47137
    Prev
    Next
    INDEX
    Explanations

    Roman

    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
    (password
    -0.08
    Password
    -0.08
    .Statement
    -0.08
    密码
    -0.08
    .Client
    -0.07
    (Exception
    -0.07
    Expired
    -0.07
    Club
    -0.07
     towel
    -0.07
    OLS
    -0.07
    POSITIVE LOGITS
     deity
    0.16
     देवी
    0.16
     goddess
    0.15
     దేవ
    0.14
     ದೇವ
    0.14
     gods
    0.14
    เทพ
    0.14
     દેવ
    0.13
     бог
    0.13
     দেব
    0.13
    Activations Density 0.039%

    No Known Activations