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. 76372
    Prev
    Next
    INDEX
    Explanations

    Interlaced video and rates

    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
     simpler
    -0.08
    /simple
    -0.08
    (simple
    -0.08
    ುತ್ತದೆ
    -0.07
     conj
    -0.07
    684
    -0.07
    /ioutil
    -0.07
    larını
    -0.07
    _prior
    -0.07
     lunch
    -0.07
    POSITIVE LOGITS
     Hz
    0.11
    Hz
    0.10
     Baltimore
    0.09
     fréquence
    0.09
     Braun
    0.09
     中国
    0.09
     בישראל
    0.08
     mains
    0.08
     كهرب
    0.08
    .frequency
    0.08
    Activations Density 0.003%

    No Known Activations