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. 15-RESID-POST-AA
    6. 19005
    Prev
    Next
    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archical
    -0.08
    nen
    -0.08
     NEC
    -0.07
     ABC
    -0.07
     astronom
    -0.07
     ব্যক্তি
    -0.07
    ách
    -0.07
     checkbox
    -0.07
    atic
    -0.07
     astronomical
    -0.07
    POSITIVE LOGITS
     conco
    0.08
    גר
    0.08
    שר
    0.08
    වා
    0.08
    ()?>
    0.08
    עלות
    0.08
     disso
    0.08
    аду
    0.08
    hoko
    0.08
     goûts
    0.08
    Activations Density 0.002%

    No Known Activations