© 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. 19-RESID-POST-AA
    11. 18550
    Prev
    Next
    INDEX
    Explanations

    free

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    イトル
    -0.08
    監
    -0.08
    екса
    -0.08
    ៈ
    -0.08
    CRIPTION
    -0.08
     siitä
    -0.07
     monitoring
    -0.07
     säker
    -0.07
    édiaire
    -0.07
     conseguido
    -0.07
    POSITIVE LOGITS
     spirits
    0.14
    -thinking
    0.14
     التفكير
    0.13
     spirited
    0.13
     spirit
    0.12
     espíritu
    0.12
     pensamiento
    0.12
     thinkers
    0.11
    思想
    0.11
     souls
    0.11
    Activations Density 0.007%

    No Known Activations