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. 102914
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    gain
    -0.08
    <Big
    -0.08
    abilis
    -0.07
    <this
    -0.07
    <Type
    -0.07
    ợp
    -0.07
    orthy
    -0.07
    <Key
    -0.07
    _MARGIN
    -0.07
    anei
    -0.07
    POSITIVE LOGITS
     preci
    0.09
     servi
    0.08
     Encore
    0.07
     maksimum
    0.07
     managed
    0.07
     restantes
    0.07
     celery
    0.07
     May
    0.07
     لدينا
    0.07
     Managed
    0.07
    Activations Density 0.040%

    No Known Activations