© 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. 50839
    Prev
    Next
    INDEX
    Explanations

    say "ресс" words

    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
     voc
    -0.08
    oy
    -0.08
    culo
    -0.08
    коп
    -0.07
    owaniu
    -0.07
    ployer
    -0.07
    ctr
    -0.07
     invol
    -0.07
    JPY
    -0.07
    [counter
    -0.07
    POSITIVE LOGITS
    ressive
    0.17
    ression
    0.17
    resión
    0.16
    рессив
    0.16
    ressant
    0.14
    ресс
    0.14
    pressive
    0.12
    RESSED
    0.12
    resi
    0.11
    ressed
    0.11
    Activations Density 0.001%

    No Known Activations