© 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. 2707
    Prev
    Next
    INDEX
    Explanations

    herd

    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
     fiss
    -0.08
     hed
    -0.08
     Kirst
    -0.08
     Punt
    -0.08
    င္း
    -0.08
     szá
    -0.08
     verr
    -0.08
    Victoria
    -0.08
    jš
    -0.07
    vanje
    -0.07
    POSITIVE LOGITS
     Cl
    0.07
     পর
    0.07
     chol
    0.07
    -desc
    0.07
    ลูก
    0.07
     chromosomes
    0.07
     needles
    0.07
     వర
    0.07
    qid
    0.07
    QR
    0.06
    Activations Density 0.001%

    No Known Activations