© 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. 96807
    Prev
    Next
    INDEX
    Explanations

    say "om" or "asm" 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
    iansand
    -0.09
     болатын
    -0.08
    ption
    -0.08
    _complex
    -0.08
    icamente
    -0.08
     diz
    -0.08
    udis
    -0.08
    iang
    -0.08
    plit
    -0.08
     coral
    -0.08
    POSITIVE LOGITS
    oms
    0.14
    asm
    0.11
    oming
    0.10
    OM
    0.10
    omp
    0.10
    ommen
    0.09
    ASM
    0.09
    omh
    0.09
    omb
    0.09
    ombra
    0.09
    Activations Density 0.002%

    No Known Activations