© 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. 102965
    Prev
    Next
    INDEX
    Explanations

    means

    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
    और
    -0.13
    및
    -0.13
    そして
    -0.12
    અને
    -0.12
     மற்றும்
    -0.11
     என்ப
    -0.11
    하거나
    -0.11
    etc
    -0.11
    ".↵
    -0.11
    \\.
    -0.10
    POSITIVE LOGITS
     the
    0.29
     we
    0.24
     that
    0.23
     it's
    0.23
     there's
    0.23
    :↵↵
    0.20
     there
    0.20
     they
    0.19
     a
    0.19
     we're
    0.17
    Activations Density 0.058%

    No Known Activations