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. 56170
    Prev
    Next
    INDEX
    Explanations

    1

    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
     shout
    -0.10
     waistband
    -0.08
     commission
    -0.08
     Commission
    -0.08
     assembler
    -0.08
     👍
    -0.08
     judicial
    -0.08
    ilé
    -0.08
    Multiplier
    -0.08
    Allocated
    -0.07
    POSITIVE LOGITS
     computes
    0.08
    _DC
    0.08
     Drawing
    0.07
    _ch
    0.07
    자동
    0.07
     =~
    0.07
     ziehen
    0.07
    fügung
    0.07
    DCF
    0.07
    xref
    0.07
    Activations Density 0.021%

    No Known Activations