© 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. 94919
    Prev
    Next
    INDEX
    Explanations

    波

    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
     BEN
    -0.08
     borderline
    -0.08
     Depart
    -0.08
     unve
    -0.07
     Moe
    -0.07
     motto
    -0.07
     unveiling
    -0.07
    别人
    -0.07
     kapital
    -0.07
     Alexandra
    -0.07
    POSITIVE LOGITS
    stig
    0.08
    heiten
    0.08
    лан
    0.08
    edges
    0.08
    Stereo
    0.07
     isot
    0.07
    age
    0.07
     Arro
    0.07
    ذة
    0.07
    inc
    0.07
    Activations Density 0.004%

    No Known Activations