© 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. 19-RESID-POST-AA
    11. 18651
    Prev
    Next
    INDEX
    Explanations

    combine

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    альное
    -0.08
    alat
    -0.08
    apala
    -0.08
    afuta
    -0.08
    fte
    -0.07
    a
    -0.07
    альная
    -0.07
    revet
    -0.07
    енции
    -0.07
    фт
    -0.07
    POSITIVE LOGITS
     into
    0.21
    Into
    0.17
    _into
    0.17
     Into
    0.16
     them
    0.15
     INTO
    0.14
     two
    0.13
     disparate
    0.13
     these
    0.13
    两个
    0.13
    Activations Density 0.015%

    No Known Activations