© 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. 23-RESID-POST-AA
    11. 48196
    Prev
    Next
    INDEX
    Explanations

    say number 7

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nab
    -0.08
     বৃদ্ধ
    -0.08
    Bout
    -0.07
    Opt
    -0.07
     expon
    -0.07
     orientation
    -0.07
    /.
    -0.07
    >.
    -0.07
    OUTH
    -0.07
    Hair
    -0.07
    POSITIVE LOGITS
     dragons
    0.09
    ogenic
    0.09
     első
    0.08
     lada
    0.08
     amic
    0.08
    _prime
    0.08
     primes
    0.08
     estruturas
    0.08
    کا
    0.08
     primo
    0.08
    Activations Density 0.007%

    No Known Activations