© 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. 95195
    Prev
    Next
    INDEX
    Explanations

    NAD

    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
    virti
    -0.08
     ಅಮ
    -0.08
     Nigerian
    -0.08
     nwoke
    -0.08
     ವಿಚ
    -0.08
     Antoine
    -0.08
     zom
    -0.08
     chicks
    -0.08
    caught
    -0.08
     atrak
    -0.07
    POSITIVE LOGITS
     Optional
    0.09
    ---
    0.09
    /output
    0.08
    .entity
    0.07
     ---
    0.07
    @Entity
    0.07
     func
    0.07
    �
    0.07
     maint
    0.07
     OPTIONAL
    0.07
    Activations Density 0.000%

    No Known Activations