© 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. 78324
    Prev
    Next
    INDEX
    Explanations

    qualitative

    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
     Př
    -0.08
    erman
    -0.08
     treasure
    -0.08
    男人
    -0.08
    music
    -0.08
     muslim
    -0.08
     menj
    -0.08
     aufreg
    -0.08
     punya
    -0.07
     manche
    -0.07
    POSITIVE LOGITS
     qualitative
    0.16
     qualit
    0.16
     Qual
    0.12
     qualitat
    0.11
     kwalitat
    0.11
    Qual
    0.11
    qual
    0.09
     anecd
    0.08
     cual
    0.08
     scouting
    0.08
    Activations Density 0.099%

    No Known Activations