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. 29911
    Prev
    Next
    INDEX
    Explanations

    Out

    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
     independent
    -0.08
    QE
    -0.07
     communic
    -0.07
     kommun
    -0.07
    -0.07
    _LENGTH
    -0.07
     trims
    -0.07
    חשב
    -0.07
     length
    -0.07
     Django
    -0.07
    POSITIVE LOGITS
     воде
    0.10
     abaste
    0.09
     Emerg
    0.08
     Advertising
    0.08
    みに
    0.08
    landi
    0.08
     Land
    0.08
    вах
    0.08
     scientifiques
    0.08
    icao
    0.08
    Activations Density 0.001%

    No Known Activations