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. 120202
    Prev
    Next
    INDEX
    Explanations

    types and classifications

    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
    contained
    -0.08
     터
    -0.07
    午
    -0.07
     inyong
    -0.07
    飛
    -0.07
    ocu
    -0.07
     ถึง
    -0.07
    Mapper
    -0.07
     午
    -0.07
    ują
    -0.07
    POSITIVE LOGITS
     según
    0.11
     разновид
    0.10
     TYPES
    0.10
     Types
    0.10
     المختلفة
    0.10
     Arten
    0.10
     moods
    0.10
     бывают
    0.10
    /types
    0.10
     principali
    0.10
    Activations Density 0.099%

    No Known Activations