© 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. 102996
    Prev
    Next
    INDEX
    Explanations

    foreign 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
     narratives
    -0.08
    uild
    -0.08
    ARDS
    -0.07
     naye
    -0.07
     pushing
    -0.07
     nuevas
    -0.07
     afrontar
    -0.07
    édito
    -0.07
    precedented
    -0.07
     FAQs
    -0.07
    POSITIVE LOGITS
     scheint
    0.08
     попыт
    0.08
     tentou
    0.08
     происходит
    0.08
     atriz
    0.08
     tätig
    0.08
     tente
    0.08
     gevangen
    0.08
     sitzt
    0.08
     geprobeerd
    0.07
    Activations Density 0.000%

    No Known Activations