© 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. 3-RESID-POST-AA
    11. 1517
    Prev
    Next
    INDEX
    Explanations

    .*;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ог
    -0.09
     linda
    -0.08
     känner
    -0.08
     писал
    -0.07
     وص
    -0.07
     kennis
    -0.07
    \uc
    -0.07
    ถึง
    -0.07
    stip
    -0.07
     wb
    -0.07
    POSITIVE LOGITS
     Mar
    0.08
    νή
    0.07
     Capt
    0.07
     άρθ
    0.07
    XML
    0.07
     CAPS
    0.07
     sheen
    0.07
    .res
    0.07
    ieke
    0.07
     CFG
    0.06
    Activations Density 0.000%

    No Known Activations