© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44385
    Prev
    Next
    INDEX
    Explanations

    reason

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Entrega
    -0.08
    Cond
    -0.08
    ineq
    -0.08
     aw
    -0.08
    essay
    -0.07
    queeze
    -0.07
     cone
    -0.07
    Ent
    -0.07
     empre
    -0.07
    _cond
    -0.07
    POSITIVE LOGITS
    ذا
    0.09
     Twilight
    0.08
     Sherlock
    0.08
    ётся
    0.08
    ثال
    0.08
     Parkinson
    0.08
     cia
    0.07
     hacen
    0.07
    theros
    0.07
     Tort
    0.07
    Activations Density 0.006%

    No Known Activations