© 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. 48007
    Prev
    Next
    INDEX
    Explanations

    omos, imos

    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
    icals
    -0.11
    ierd
    -0.09
    eneuve
    -0.09
     dle
    -0.09
    icates
    -0.08
     целей
    -0.08
    endees
    -0.08
    icate
    -0.08
    icap
    -0.08
    ial
    -0.08
    POSITIVE LOGITS
    omos
    0.11
    imos
    0.10
    omo
    0.09
    入力
    0.08
     입력
    0.08
     入
    0.08
    输入
    0.08
    imamente
    0.07
     输入
    0.07
     enter
    0.07
    Activations Density 0.001%

    No Known Activations