© 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. 48591
    Prev
    Next
    INDEX
    Explanations

    OB/Hob

    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
    τομα
    -0.09
    viri
    -0.08
    DIM
    -0.08
    -linear
    -0.08
    -pop
    -0.08
    -mar
    -0.08
    gef
    -0.08
     Isles
    -0.08
     populate
    -0.08
     TILE
    -0.08
    POSITIVE LOGITS
    bs
    0.12
    be
    0.10
    erg
    0.10
    arts
    0.09
    urg
    0.09
    æk
    0.09
    artner
    0.09
    arth
    0.08
    ert
    0.08
    ürger
    0.08
    Activations Density 0.015%

    No Known Activations