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. 76733
    Prev
    Next
    INDEX
    Explanations

    -------

    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
    习
    -0.08
    ohan
    -0.08
    渡
    -0.08
     matrimonial
    -0.08
    ואים
    -0.08
    ार्थ
    -0.07
     universo
    -0.07
     Dent
    -0.07
     جذب
    -0.07
    _OC
    -0.07
    POSITIVE LOGITS
    chemical
    0.08
     Release
    0.07
     Qualified
    0.07
     Wann
    0.07
     basis
    0.07
     Basis
    0.07
    (fl
    0.07
     Qualifications
    0.07
     вина
    0.07
    ảm
    0.07
    Activations Density 0.001%

    No Known Activations