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. 19520
    Prev
    Next
    INDEX
    Explanations

    success

    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
     inefficient
    -0.08
     unfamiliar
    -0.07
     undone
    -0.07
    ിട
    -0.07
     inaccurate
    -0.07
     ineff
    -0.07
     inexperienced
    -0.07
    achine
    -0.07
     inadequate
    -0.07
     besluit
    -0.07
    POSITIVE LOGITS
     👍
    0.13
     Successfully
    0.12
    Successfully
    0.12
     ✅
    0.11
    successful
    0.11
    👌
    0.10
     ✓
    0.10
    Successful
    0.10
    ✓
    0.10
    成功
    0.10
    Activations Density 0.010%

    No Known Activations