© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31148
    Prev
    Next
    INDEX
    Explanations

    Diverse content

    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
    züglich
    -0.08
     haze
    -0.07
    scene
    -0.07
    LOS
    -0.07
     egw
    -0.07
    সব
    -0.07
    nearest
    -0.07
     udvalg
    -0.07
    �
    -0.07
    ACCESS
    -0.07
    POSITIVE LOGITS
     architecture
    0.08
     complain
    0.07
     Wanted
    0.07
     ресур
    0.07
     scoped
    0.07
     podcast
    0.07
     wondered
    0.07
     Iran
    0.07
     Tol
    0.07
     ик
    0.07
    Activations Density 0.000%

    No Known Activations