© 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. 5918
    Prev
    Next
    INDEX
    Explanations

    =

    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
    Categorie
    -0.09
     relaxation
    -0.08
    qp
    -0.08
     anba
    -0.08
    Layout
    -0.08
    Relation
    -0.08
    /q
    -0.07
    Kategorie
    -0.07
    Below
    -0.07
     ngaph
    -0.07
    POSITIVE LOGITS
    store
    0.08
    .store
    0.08
     ideal
    0.08
     append
    0.08
    术
    0.08
    _true
    0.07
    append
    0.07
    .append
    0.07
     rohe
    0.07
    nya
    0.07
    Activations Density 0.000%

    No Known Activations