© 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. 54893
    Prev
    Next
    INDEX
    Explanations

    Questions

    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
    quote
    -0.08
    }↵
    -0.08
    .deleted
    -0.08
    ↵    ↵
    -0.07
     acknowledgement
    -0.07
     quote
    -0.07
    .Position
    -0.07
    .Identity
    -0.07
     confirmation
    -0.07
    -Ver
    -0.07
    POSITIVE LOGITS
    哪个
    0.17
    哪个好
    0.15
     whichever
    0.14
    哪
    0.14
     favors
    0.12
    ichever
    0.12
     哪
    0.12
     compete
    0.12
     preferable
    0.11
    ちら
    0.11
    Activations Density 0.123%

    No Known Activations