© 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. 11-RESID-POST-AA
    11. 78408
    Prev
    Next
    INDEX
    Explanations

    least

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    op
    -0.08
     pros
    -0.07
    ın
    -0.07
     prevent
    -0.07
    opa
    -0.07
    irp
    -0.07
    hing
    -0.07
    (var
    -0.07
     oriental
    -0.07
    orn
    -0.07
    POSITIVE LOGITS
     sicuramente
    0.12
     certainly
    0.11
     जरूर
    0.10
     kindlasti
    0.10
     뿐
    0.10
     lisäksi
    0.10
     ועוד
    0.10
     अलावा
    0.10
    뿐
    0.10
     וגם
    0.09
    Activations Density 0.072%

    No Known Activations