© 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 EvalsExportsinterp-engineNEWAPI 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. 70891
    Prev
    Next
    INDEX
    Explanations

    out

    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
     dominant
    -0.09
    companh
    -0.08
     cartons
    -0.08
    语
    -0.07
     Aliment
    -0.07
     dívida
    -0.07
     routed
    -0.07
     Physical
    -0.07
    Quel
    -0.07
     frameworks
    -0.07
    POSITIVE LOGITS
     બેઠક
    0.08
     indication
    0.08
    -knit
    0.08
     Indicates
    0.08
     testament
    0.08
     ঘোষণা
    0.08
    �
    0.08
    iful
    0.08
     ade
    0.07
    [R
    0.07
    Activations Density 0.016%

    No Known Activations