© 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. 23-RESID-POST-AA
    11. 5959
    Prev
    Next
    INDEX
    Explanations

    cosine equations

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $file
    -0.10
    $p
    -0.10
    $t
    -0.10
    credentials
    -0.09
    FG
    -0.09
    $I
    -0.09
    thr
    -0.09
    FC
    -0.09
    bron
    -0.09
    $d
    -0.09
    POSITIVE LOGITS
     $\
    0.13
     ceil
    0.10
     \
    0.10
     atan
    0.10
    余
    0.10
     `
    0.09
     np
    0.09
     numpy
    0.09
    нында
    0.09
    angezien
    0.09
    Activations Density 0.103%

    No Known Activations