© 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. 48073
    Prev
    Next
    INDEX
    Explanations

    say "the ending .path"

    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
    @yahoo
    -0.09
     tilgjeng
    -0.08
    $username
    -0.08
     novih
    -0.08
    ={<
    -0.08
     jär
    -0.08
     almoh
    -0.08
     organs
    -0.08
     existente
    -0.08
    collections
    -0.07
    POSITIVE LOGITS
    .dirname
    0.17
    .getcwd
    0.15
    (__
    0.15
     dirname
    0.15
     BASE
    0.14
    .root
    0.14
     root
    0.14
    .cwd
    0.14
    根
    0.14
    .abspath
    0.14
    Activations Density 0.012%

    No Known Activations