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. 15-RESID-POST-AA
    6. 18966
    Prev
    Next
    INDEX
    Explanations

    /

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fork
    -0.09
     Fork
    -0.08
     remover
    -0.08
    KIN
    -0.08
    OS
    -0.07
    DET
    -0.07
    Os
    -0.07
    דיק
    -0.07
    -0.07
    Mq
    -0.07
    POSITIVE LOGITS
     শতাংশ
    0.14
    percentage
    0.14
    百分
    0.13
     percentages
    0.12
     percentage
    0.12
     प्रतिशत
    0.12
     Percentage
    0.12
     percentual
    0.11
     ശതമ
    0.11
    _percentage
    0.11
    Activations Density 0.013%

    No Known Activations