© 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. 102856
    Prev
    Next
    INDEX
    Explanations

    Duration

    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
    рана
    -0.08
    avou
    -0.08
    国务
    -0.07
     laban
    -0.07
    lą
    -0.07
     aban
    -0.07
    maximize
    -0.07
    러운
    -0.07
    fortunate
    -0.07
     sahibi
    -0.07
    POSITIVE LOGITS
     dauert
    0.30
     duurt
    0.29
     dauern
    0.25
     duration
    0.24
     مدة
    0.23
     tarda
    0.22
     demora
    0.22
     durée
    0.22
    耗
    0.22
    Duration
    0.22
    Activations Density 0.138%

    No Known Activations