© 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. 50787
    Prev
    Next
    INDEX
    Explanations

    Germanic 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
     Einzel
    -0.08
     Öl
    -0.08
    anément
    -0.08
    GLIGENCE
    -0.08
     individus
    -0.08
     débat
    -0.07
     Hof
    -0.07
    ANTE
    -0.07
    ανά
    -0.07
     Ced
    -0.07
    POSITIVE LOGITS
    erman
    0.12
    oths
    0.12
    oth
    0.11
    ermanent
    0.10
    erm
    0.10
    ರ್ಮ
    0.09
    aeilge
    0.09
    ోత
    0.08
    ర్మ
    0.08
    ermany
    0.08
    Activations Density 0.001%

    No Known Activations