© 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. 51445
    Prev
    Next
    INDEX
    Explanations

    __

    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
    ømme
    -0.08
    ointe
    -0.08
     pragma
    -0.07
     olur
    -0.07
    ब्ल
    -0.07
    wami
    -0.07
    ponde
    -0.07
    ofence
    -0.07
     координ
    -0.07
     comen
    -0.07
    POSITIVE LOGITS
    �
    0.08
    itet
    0.08
    င္
    0.07
     tshi
    0.07
    ిన
    0.07
    �
    0.07
    иски
    0.07
     CH
    0.07
    Secrets
    0.07
    .--
    0.07
    Activations Density 0.000%

    No Known Activations