© 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. 50455
    Prev
    Next
    INDEX
    Explanations

    say "er" words

    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
     pensé
    -0.08
     Fut
    -0.08
    neo
    -0.07
     Sal
    -0.07
     forhold
    -0.07
    IENTO
    -0.07
     proportion
    -0.07
     Intersection
    -0.07
    ستو
    -0.07
     Pellet
    -0.07
    POSITIVE LOGITS
    erk
    0.14
    er
    0.12
    ihkan
    0.12
    erkt
    0.10
    र्क
    0.10
    ianik
    0.09
    elf
    0.09
    ರ್ಕ
    0.09
    agli
    0.09
    agl
    0.09
    Activations Density 0.002%

    No Known Activations