© 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. 23-RESID-POST-AA
    11. 50896
    Prev
    Next
    INDEX
    Explanations

    equal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    αιρε
    -0.08
     tetep
    -0.07
     positiven
    -0.07
     tovább
    -0.07
     reina
    -0.07
    avor
    -0.07
     forset
    -0.07
    adzirisa
    -0.07
     الخير
    -0.07
    ாந்த
    -0.07
    POSITIVE LOGITS
     बराब
    0.30
     comparable
    0.29
     equal
    0.29
     igual
    0.29
     égal
    0.27
    equal
    0.27
    匹
    0.26
     rival
    0.26
    Equal
    0.25
     Equal
    0.25
    Activations Density 0.114%

    No Known Activations