© 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 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. 112523
    Prev
    Next
    INDEX
    Explanations

    telling

    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
     perish
    -0.08
     subway
    -0.08
     wiki
    -0.07
    یات
    -0.07
     papers
    -0.07
    sources
    -0.07
     میری
    -0.07
     Barnes
    -0.07
     cite
    -0.07
     semifinal
    -0.07
    POSITIVE LOGITS
     bouts
    0.08
    ıp
    0.07
    öst
    0.07
    anych
    0.07
     Rhodes
    0.07
     принят
    0.07
     Anzeige
    0.07
    going
    0.07
     scrolling
    0.07
    EMU
    0.07
    Activations Density 0.000%

    No Known Activations