© 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. 72
    Prev
    Next
    INDEX
    Explanations

    clipboard

    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
    Archive
    -0.08
     anticipation
    -0.08
     bailout
    -0.08
    Interpolation
    -0.08
     sociedades
    -0.08
     estate
    -0.07
    步
    -0.07
     interoperability
    -0.07
     refugee
    -0.07
     interpolate
    -0.07
    POSITIVE LOGITS
     Flush
    0.08
     installé
    0.08
     Drink
    0.08
     installiert
    0.08
     toen
    0.08
     설치
    0.08
     Install
    0.08
     Jung
    0.07
     Rose
    0.07
     Freud
    0.07
    Activations Density 0.002%

    No Known Activations