© 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. 129532
    Prev
    Next
    INDEX
    Explanations

    golems

    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
    考试
    -0.08
     negli
    -0.08
     exams
    -0.08
     essays
    -0.08
    его
    -0.08
     messen
    -0.08
     varying
    -0.07
    .exam
    -0.07
     complicated
    -0.07
    _ME
    -0.07
    POSITIVE LOGITS
    refer
    0.08
    Boy
    0.08
    Readable
    0.07
     doubl
    0.07
     Florian
    0.07
    规模
    0.07
    culate
    0.07
    bec
    0.07
     mpg
    0.07
     broke
    0.07
    Activations Density 0.001%

    No Known Activations