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. 109153
    Prev
    Next
    INDEX
    Explanations

    script/dialogue creation

    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
     reinstall
    -0.09
     Installation
    -0.08
    _install
    -0.08
     Installing
    -0.08
    _FAILED
    -0.08
     финанс
    -0.08
     Imaging
    -0.08
     protège
    -0.08
     установка
    -0.08
     площадь
    -0.08
    POSITIVE LOGITS
     الحوار
    0.14
    Dialogue
    0.12
     dialogue
    0.12
    Conversation
    0.11
     conversational
    0.11
     diálogo
    0.11
     Dialogue
    0.11
     conversation
    0.10
     گفتگو
    0.10
     Conversation
    0.10
    Activations Density 0.037%

    No Known Activations