© 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. 11-RESID-POST-AA
    11. 94997
    Prev
    Next
    INDEX
    Explanations

    ln

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     named
    -0.08
     public
    -0.08
    Qualified
    -0.08
     third
    -0.07
    !
    -0.07
    Builder
    -0.07
    Named
    -0.07
     verb
    -0.07
     nom
    -0.07
     sixth
    -0.07
    POSITIVE LOGITS
    趋
    0.14
     meningkat
    0.11
     nearing
    0.11
     approaching
    0.11
     poveć
    0.10
     tends
    0.10
     proximité
    0.10
     increasingly
    0.10
     가까
    0.10
     dominating
    0.10
    Activations Density 0.027%

    No Known Activations