© 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. 51167
    Prev
    Next
    INDEX
    Explanations

    Spanish language

    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
     règ
    -0.09
    IONE
    -0.08
    iei
    -0.08
     io
    -0.08
    unye
    -0.08
    ios
    -0.08
     décl
    -0.08
     bu
    -0.08
     αι
    -0.07
     ts
    -0.07
    POSITIVE LOGITS
    jo
    0.17
    j
    0.16
    jos
    0.16
    jería
    0.16
    jí
    0.15
    jado
    0.15
    ja
    0.15
    jem
    0.15
    je
    0.15
    jada
    0.15
    Activations Density 0.011%

    No Known Activations