© 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. 19-RESID-POST-AA
    11. 102670
    Prev
    Next
    INDEX
    Explanations

    hyphenated words

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مختلف
    -0.08
     llevando
    -0.08
     تبدیل
    -0.07
     Reverse
    -0.07
    ующим
    -0.07
     höheren
    -0.07
     kuruluş
    -0.07
     Cra
    -0.07
    fidh
    -0.07
     जाते
    -0.07
    POSITIVE LOGITS
    -to
    0.14
    –
    0.13
    -empty
    0.12
    both
    0.12
    -English
    0.12
    -क
    0.12
    +/
    0.12
    Both
    0.11
    �
    0.11
    ->
    0.11
    Activations Density 0.022%

    No Known Activations