© 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. 3-RESID-POST-AA
    11. 12767
    Prev
    Next
    INDEX
    Explanations

    Settlements, settling, text beginnings/endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Unavailable
    -0.08
    Emitter
    -0.07
    .API
    -0.07
     slightest
    -0.07
    Responses
    -0.07
    Weak
    -0.07
     выгля
    -0.07
     раскры
    -0.07
    .Timer
    -0.07
     IF
    -0.07
    POSITIVE LOGITS
     sabores
    0.08
    烟
    0.08
     trustees
    0.08
    保障
    0.08
    တ်
    0.08
     tattoos
    0.08
    残局
    0.08
     bitcoins
    0.07
     gratifying
    0.07
     الأمور
    0.07
    Activations Density 0.030%

    No Known Activations