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

    Neuronpedia

    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. 45470
    Prev
    Next
    INDEX
    Explanations

    Geometry lines

    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
    _nonce
    -0.08
     £
    -0.07
     (£
    -0.07
    അ
    -0.07
    .payment
    -0.07
    :bold
    -0.07
     அத
    -0.07
     sterling
    -0.07
    具
    -0.07
     Voc
    -0.07
    POSITIVE LOGITS
     openness
    0.09
     fenced
    0.09
     continual
    0.09
     integrations
    0.08
     zig
    0.08
     isolated
    0.08
     desaparecer
    0.08
     seg
    0.08
    Contour
    0.08
     Complexity
    0.08
    Activations Density 0.018%

    No Known Activations