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. 77570
    Prev
    Next
    INDEX
    Explanations

    damage

    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
     bure
    -0.09
     spending
    -0.08
     Spending
    -0.07
     luminos
    -0.07
     sv
    -0.07
     Lum
    -0.07
     Bing
    -0.07
     pave
    -0.07
     Pla
    -0.07
    Initi
    -0.07
    POSITIVE LOGITS
    是多少
    0.09
     Reduction
    0.09
     reduction
    0.08
    -bearing
    0.08
    Reduction
    0.08
    压
    0.08
    දු
    0.08
    ible
    0.08
     Coconut
    0.08
    ífica
    0.08
    Activations Density 0.005%

    No Known Activations