© 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. 65340
    Prev
    Next
    INDEX
    Explanations

    artistic roles and leadership

    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
    -enh
    -0.09
    -filled
    -0.08
    650
    -0.08
    Please
    -0.07
     sau
    -0.07
    5
    -0.07
     propensity
    -0.07
     please
    -0.07
    ń
    -0.07
     pelvis
    -0.07
    POSITIVE LOGITS
    ajah
    0.09
     koffie
    0.09
     Gibt
    0.08
     აკ
    0.08
     gestellt
    0.08
    jajo
    0.08
     �
    0.08
     shouted
    0.08
     Mature
    0.08
     Teens
    0.08
    Activations Density 0.022%

    No Known Activations