Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112457
    Prev
    Next
    INDEX
    Explanations

    geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     прок
    -0.08
     rezept
    -0.08
     applaud
    -0.07
    tap
    -0.07
    udar
    -0.07
     continuing
    -0.07
     sín
    -0.07
     τά
    -0.07
    rement
    -0.07
    alsa
    -0.07
    POSITIVE LOGITS
    三
    0.13
     triangle
    0.12
    _triangle
    0.11
    三个
    0.11
     ત્રણ
    0.11
     Triangle
    0.10
    .vertices
    0.10
     మూడు
    0.10
     triangles
    0.10
     vertices
    0.10
    Activations Density 0.068%

    No Known Activations