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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6013
    Prev
    Next
    INDEX
    Explanations

    say "ч" 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
    rlige
    -0.09
    int
    -0.08
    mek
    -0.08
    nent
    -0.08
    නා
    -0.08
    ném
    -0.08
    mentation
    -0.08
    -int
    -0.08
    nere
    -0.08
    skem
    -0.08
    POSITIVE LOGITS
    чна
    0.09
    ч
    0.09
    чны
    0.08
    ча
    0.08
     Oliveira
    0.08
    чен
    0.08
    чно
    0.08
    igest
    0.08
    чный
    0.08
    ples
    0.07
    Activations Density 0.001%

    No Known Activations