© 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. 29621
    Prev
    Next
    INDEX
    Explanations

    enough

    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
    াকার
    -0.07
    ix
    -0.07
    ixe
    -0.07
     Vos
    -0.07
     competitor
    -0.07
     sincer
    -0.07
     sax
    -0.07
    осков
    -0.07
     Dough
    -0.07
    pesas
    -0.07
    POSITIVE LOGITS
    atlan
    0.08
    湾
    0.08
     স্ব
    0.07
     چې
    0.07
     CHA
    0.07
    、更
    0.07
     rei
    0.07
     landet
    0.07
     పాల
    0.07
    Cancelable
    0.07
    Activations Density 0.014%

    No Known Activations