© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24966
    Prev
    Next
    INDEX
    Explanations

    grandmothers and mothers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Auch
    -0.08
    აღ
    -0.08
     Aba
    -0.08
    .dc
    -0.08
    Ug
    -0.08
    piro
    -0.08
    .TABLE
    -0.08
    Waxaa
    -0.08
    Authorities
    -0.08
     IX
    -0.08
    POSITIVE LOGITS
     zve
    0.08
    igkeits
    0.07
     will
    0.07
    ’ll
    0.07
     hinzufügen
    0.07
    ’re
    0.07
     continuum
    0.07
     nebo
    0.07
     überprüfen
    0.07
    essian
    0.07
    Activations Density 0.000%

    No Known Activations