© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 63908
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
    871
    -0.08
     società
    -0.08
    টির
    -0.08
    ೊಂದ
    -0.08
    867
    -0.08
    _FA
    -0.07
    lerinin
    -0.07
    urso
    -0.07
     ggf
    -0.07
    ibern
    -0.07
    POSITIVE LOGITS
     divisible
    0.09
     Princes
    0.08
    rather
    0.08
     опера
    0.08
    instead
    0.07
     превыш
    0.07
     strictly
    0.07
     وليس
    0.07
     alak
    0.07
     Allow
    0.07
    Activations Density 0.036%

    No Known Activations