© 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. 103117
    Prev
    Next
    INDEX
    Explanations

    how

    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
    以下简称
    -0.08
    ized
    -0.08
     tähän
    -0.08
     Aucun
    -0.08
    -esque
    -0.08
     demikian
    -0.08
    extended
    -0.08
    -Based
    -0.07
    -with
    -0.07
    -inspired
    -0.07
    POSITIVE LOGITS
     how
    0.36
     كيفية
    0.30
     כיצד
    0.29
     whether
    0.29
     איך
    0.28
     cómo
    0.28
     hvordan
    0.28
     hvernig
    0.27
    如何
    0.27
     bagaimana
    0.27
    Activations Density 0.264%

    No Known Activations