© 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. 51425
    Prev
    Next
    INDEX
    Explanations

    ys

    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
    itr
    -0.08
    ochemical
    -0.08
    sigma
    -0.08
    hmen
    -0.08
    we
    -0.08
     sigma
    -0.07
    [u
    -0.07
    mat
    -0.07
    -per
    -0.07
    spr
    -0.07
    POSITIVE LOGITS
    ic
    0.11
    icacité
    0.08
     Love
    0.08
     polit
    0.08
     love
    0.08
     爱
    0.08
    ostasis
    0.08
    icent
    0.08
     ochron
    0.08
    tonu
    0.07
    Activations Density 0.001%

    No Known Activations