© 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. 6104
    Prev
    Next
    INDEX
    Explanations

    tro

    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
     kür
    -0.08
     banda
    -0.08
     эш
    -0.07
     vraag
    -0.07
    割
    -0.07
     bidang
    -0.07
    ραπε
    -0.07
     kurze
    -0.07
    аныш
    -0.07
     zang
    -0.07
    POSITIVE LOGITS
    isième
    0.13
    vatore
    0.11
    tro
    0.10
    caire
    0.10
    jans
    0.09
    adier
    0.09
    cando
    0.09
    endous
    0.09
     Trop
    0.09
    нир
    0.09
    Activations Density 0.027%

    No Known Activations