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. 76899
    Prev
    Next
    INDEX
    Explanations

    shortcut

    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
     séries
    -0.09
     Bayesian
    -0.08
     Fourier
    -0.08
     series
    -0.08
    _MPI
    -0.08
     FFT
    -0.08
    -series
    -0.08
     epistem
    -0.07
     série
    -0.07
    framework
    -0.07
    POSITIVE LOGITS
     Clicking
    0.11
     Shortcut
    0.11
     클릭
    0.10
     desktop
    0.10
    Desktop
    0.10
     Launcher
    0.10
     clickable
    0.10
     verschen
    0.10
     executable
    0.10
     onclick
    0.10
    Activations Density 0.007%

    No Known Activations