© 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. 102693
    Prev
    Next
    INDEX
    Explanations

    know

    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
    ">↵↵↵
    -0.08
     adjusts
    -0.08
     подел
    -0.08
    );↵↵↵//
    -0.08
     подбор
    -0.08
     فراهم
    -0.08
     etc
    -0.08
     спраш
    -0.07
    (reference
    -0.07
    した
    -0.07
    POSITIVE LOGITS
     enhver
    0.10
     hægt
    0.09
     আমি
    0.09
     আমরা
    0.09
     আনন্দ
    0.08
     there's
    0.08
     I
    0.08
     there
    0.08
     thata
    0.08
    ，大
    0.08
    Activations Density 0.002%

    No Known Activations