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. 65457
    Prev
    Next
    INDEX
    Explanations

    value

    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
     Cruc
    -0.09
     Mr
    -0.08
     profiles
    -0.08
    rd
    -0.08
     सदस्य
    -0.08
    _MEMBER
    -0.08
    mael
    -0.07
     Savage
    -0.07
     butterfly
    -0.07
     escl
    -0.07
    POSITIVE LOGITS
    ांकन
    0.09
     Domino
    0.08
    是多少
    0.08
     gluc
    0.08
    Comparator
    0.07
     افز
    0.07
    들을
    0.07
     tin
    0.07
    -added
    0.07
     �
    0.07
    Activations Density 0.048%

    No Known Activations