© 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. 50360
    Prev
    Next
    INDEX
    Explanations

    response

    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
    랫폼
    -0.09
    ólico
    -0.09
    릭
    -0.09
    로운
    -0.08
    riti
    -0.08
    리고
    -0.08
    осс
    -0.08
    ageno
    -0.08
    ighton
    -0.08
    lei
    -0.08
    POSITIVE LOGITS
    กลับ
    0.10
     terhadap
    0.10
     to
    0.10
    .ok
    0.10
    迅
    0.09
     ndaj
    0.09
    .reply
    0.09
    (Response
    0.09
     inmediata
    0.09
     afirm
    0.09
    Activations Density 0.059%

    No Known Activations