© 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. 96680
    Prev
    Next
    INDEX
    Explanations

    set

    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
     মন
    -0.08
     cyf
    -0.08
    yna
    -0.08
     społ
    -0.08
    apy
    -0.07
    DS
    -0.07
     mutable
    -0.07
     cx
    -0.07
    .youtube
    -0.07
    yn
    -0.07
    POSITIVE LOGITS
     supply
    0.08
     imọ
    0.07
     губер
    0.07
    Supply
    0.07
     ಸೇರಿದ
    0.07
     Supplies
    0.07
     комиссия
    0.07
     logró
    0.07
    ría
    0.07
     kirjo
    0.07
    Activations Density 0.002%

    No Known Activations