© 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. 91228
    Prev
    Next
    INDEX
    Explanations

    haze

    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
    ("\\
    -0.07
     zás
    -0.07
    (byte
    -0.07
    cciones
    -0.07
     adv
    -0.07
     email
    -0.07
     family's
    -0.07
     symmetry
    -0.07
     standpoint
    -0.07
     schoenen
    -0.07
    POSITIVE LOGITS
     translucent
    0.08
     tropical
    0.08
     cosy
    0.08
     blonde
    0.08
    滋
    0.08
     frit
    0.08
     chic
    0.08
     neon
    0.07
     Arro
    0.07
    eyey
    0.07
    Activations Density 0.002%

    No Known Activations