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. 45131
    Prev
    Next
    INDEX
    Explanations

    Filler words

    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
    :ss
    -0.08
     another
    -0.07
    ',['
    -0.07
     Бог
    -0.07
     always
    -0.07
     همیشه
    -0.07
     количество
    -0.07
     gold
    -0.06
    .gold
    -0.06
     sting
    -0.06
    POSITIVE LOGITS
     Jér
    0.10
     Lumi
    0.09
     Northampton
    0.09
    Jer
    0.08
     pressão
    0.08
     machin
    0.08
     Junction
    0.08
     JOUR
    0.08
     Evel
    0.08
    acia
    0.08
    Activations Density 0.000%

    No Known Activations