© 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. 63414
    Prev
    Next
    INDEX
    Explanations

    model

    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
     ego
    -0.08
     elite
    -0.07
    cci
    -0.07
     Pere
    -0.07
     Corpus
    -0.07
     lòng
    -0.07
     ide
    -0.07
     eki
    -0.07
     Fortress
    -0.07
     narratives
    -0.07
    POSITIVE LOGITS
    ….↵
    0.09
    anbieter
    0.08
    =w
    0.08
    Been
    0.07
     Valentine
    0.07
    ’accord
    0.07
     _.
    0.07
    börse
    0.07
     காத
    0.07
    Sounds
    0.07
    Activations Density 0.000%

    No Known Activations