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. 9067
    Prev
    Next
    INDEX
    Explanations

    newline characters

    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
     jewelry
    -0.09
     jewellery
    -0.09
    ómica
    -0.09
    摆
    -0.09
     ally
    -0.08
     Procurement
    -0.08
     Deput
    -0.08
     Diamonds
    -0.08
     Jewelry
    -0.08
     Deputy
    -0.08
    POSITIVE LOGITS
     newline
    0.15
    newline
    0.09
    _utf
    0.09
     Unix
    0.09
     termin
    0.08
     termination
    0.08
     '\
    0.08
     Unicode
    0.08
     Stimmung
    0.08
     UTF
    0.08
    Activations Density 0.005%

    No Known Activations