© 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. 51382
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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
     ranks
    -0.07
    -0.07
     dialing
    -0.07
    Rank
    -0.07
    /head
    -0.07
    -0.07
    .inc
    -0.07
    odox
    -0.07
     symmetrical
    -0.07
    ►
    -0.07
    POSITIVE LOGITS
    .React
    0.08
     Изра
    0.08
    React
    0.08
     Kor
    0.08
    ouverte
    0.08
    avec
    0.08
    환경
    0.08
    rogate
    0.08
     milie
    0.08
    爰
    0.08
    Activations Density 0.001%
    No Known Activations