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. 42028
    Prev
    Next
    INDEX
    Explanations

    FFT signal processing

    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
    Descriptions
    -0.08
     mundane
    -0.08
    MY
    -0.08
     duo
    -0.08
     Montes
    -0.08
     Myers
    -0.07
     nourishing
    -0.07
     vertreten
    -0.07
     міс
    -0.07
    .validation
    -0.07
    POSITIVE LOGITS
     FFT
    0.14
     fft
    0.13
    FFT
    0.12
     Fourier
    0.11
    _fft
    0.11
    fft
    0.09
    zah
    0.08
    傅
    0.08
     Vand
    0.08
    abah
    0.08
    Activations Density 0.003%

    No Known Activations