© 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. 3-RESID-POST-AA
    11. 2581
    Prev
    Next
    INDEX
    Explanations

    abnormal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umin
    -0.08
     envelop
    -0.08
    iger
    -0.07
     illumin
    -0.07
     partic
    -0.07
     sağlay
    -0.07
    umes
    -0.07
    inel
    -0.07
    egment
    -0.07
    ordered
    -0.07
    POSITIVE LOGITS
    FU
    0.08
    142
    0.07
     eun
    0.07
     keen
    0.07
     TD
    0.07
     Keen
    0.07
    Fin
    0.07
     odor
    0.07
    AGS
    0.07
     Dw
    0.07
    Activations Density 0.001%

    No Known Activations