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. 102842
    Prev
    Next
    INDEX
    Explanations

    Spartan

    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
     rtl
    -0.08
     ASE
    -0.08
    QC
    -0.08
     Spain
    -0.07
    �
    -0.07
     कत
    -0.07
     cau
    -0.07
     sumar
    -0.07
     suma
    -0.07
    _where
    -0.07
    POSITIVE LOGITS
     farewell
    0.08
    ιών
    0.08
     Wilder
    0.08
    Herr
    0.07
    ιν
    0.07
    _HANDLER
    0.07
    ీలు
    0.07
    떠
    0.07
     concentration
    0.07
     Beweg
    0.07
    Activations Density 0.003%

    No Known Activations