© 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. 23-RESID-POST-AA
    11. 50131
    Prev
    Next
    INDEX
    Explanations

    ко

    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
     llev
    -0.08
     EXP
    -0.07
    .less
    -0.07
     Lact
    -0.07
    eryl
    -0.07
     prvi
    -0.07
    tekst
    -0.07
    .AR
    -0.07
    encv
    -0.07
     паст
    -0.07
    POSITIVE LOGITS
    раб
    0.08
    ఏ
    0.08
    zisa
    0.07
    zig
    0.07
    హ
    0.07
    noch
    0.07
     factories
    0.07
    應
    0.07
     ibang
    0.07
    isestä
    0.07
    Activations Density 0.000%

    No Known Activations