© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6080
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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
    ional
    -0.08
    luent
    -0.08
    lid
    -0.08
    hanga
    -0.07
    -be
    -0.07
    lıq
    -0.07
    baix
    -0.07
    hu
    -0.07
    l
    -0.07
    lace
    -0.07
    POSITIVE LOGITS
    яла
    0.12
    яло
    0.11
    ownie
    0.11
    ельзя
    0.11
    яли
    0.11
    ять
    0.11
    Я
    0.10
    ял
    0.10
    ести
    0.10
    если
    0.09
    Activations Density 0.003%

    No Known Activations