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. 78532
    Prev
    Next
    INDEX
    Explanations

    frequency

    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
     amput
    -0.08
    _stmt
    -0.08
    �
    -0.07
     redirected
    -0.07
    Stmt
    -0.07
    判断
    -0.07
     affirmation
    -0.07
    lined
    -0.07
     tote
    -0.07
    美容
    -0.07
    POSITIVE LOGITS
     Hz
    0.12
    Hz
    0.10
     GHz
    0.10
    GHz
    0.10
     ω
    0.10
     Puls
    0.09
     waveform
    0.09
     Frequency
    0.09
     Tempo
    0.09
    frequency
    0.09
    Activations Density 0.006%

    No Known Activations