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. 7-RESID-POST-AA
    6. 1681
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     מדובר
    -0.08
     interne
    -0.08
     hypothesis
    -0.08
     Chen
    -0.08
    geschoss
    -0.07
     formative
    -0.07
     הגב
    -0.07
     Heidel
    -0.07
    мн
    -0.07
    angs
    -0.07
    POSITIVE LOGITS
    Soon
    0.08
    �
    0.07
    Accel
    0.07
     rece
    0.07
    Pel
    0.07
    DMA
    0.07
    mem
    0.07
     olmad
    0.07
    pel
    0.07
    ̆
    0.07
    Activations Density 0.333%

    No Known Activations