© 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. 51588
    Prev
    Next
    INDEX
    Explanations

    environment

    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
    ൈന
    -0.08
    gesellschaft
    -0.08
    werken
    -0.08
    endregion
    -0.08
    人民共和国
    -0.08
    ponenten
    -0.08
     қис
    -0.07
    enness
    -0.07
    betrag
    -0.07
    率
    -0.07
    POSITIVE LOGITS
    IRONMENT
    0.24
    iorn
    0.16
    ally
    0.14
     conducive
    0.13
    iro
    0.13
    alist
    0.12
    ální
    0.12
    IRON
    0.12
    গত
    0.12
    पूर
    0.12
    Activations Density 0.043%

    No Known Activations