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. 65821
    Prev
    Next
    INDEX
    Explanations

    0

    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
    ternative
    -0.09
    .person
    -0.08
     Adu
    -0.08
     Alternative
    -0.08
     طبي
    -0.07
    seau
    -0.07
    -Pack
    -0.07
    .sun
    -0.07
     solaire
    -0.07
     φό
    -0.07
    POSITIVE LOGITS
    」「
    0.09
    HEIGHT
    0.08
     ниже
    0.08
     esconder
    0.08
     demolished
    0.08
    _axis
    0.07
    }}{{
    0.07
    0.07
     foundations
    0.07
     cornerstone
    0.07
    Activations Density 0.019%

    No Known Activations