© 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. 69300
    Prev
    Next
    INDEX
    Explanations

    -

    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
     ancestral
    -0.08
     coverage
    -0.07
    covered
    -0.07
     Cross
    -0.07
     omission
    -0.07
     surplus
    -0.07
     Bears
    -0.07
    /B
    -0.07
    Covered
    -0.07
     absence
    -0.07
    POSITIVE LOGITS
     ছোট
    0.10
     küçük
    0.09
     చిన్న
    0.09
     サイズ
    0.09
     छोट
    0.08
    ）、
    0.08
     નાના
    0.08
     mempert
    0.08
     maupun
    0.08
     kleinen
    0.08
    Activations Density 0.036%

    No Known Activations