© 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. 91386
    Prev
    Next
    INDEX
    Explanations

    and

    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
     graphic
    -0.08
     mengh
    -0.07
     před
    -0.07
    Vor
    -0.07
    .batch
    -0.07
     bone
    -0.07
     sto
    -0.07
    草
    -0.07
     hemat
    -0.07
     cite
    -0.07
    POSITIVE LOGITS
     Bahrain
    0.09
     receptions
    0.08
     Corr
    0.08
     Khal
    0.07
     Dubai
    0.07
     milit
    0.07
     intér
    0.07
     Gil
    0.07
     bode
    0.07
     Kh
    0.07
    Activations Density 0.036%

    No Known Activations