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. 90710
    Prev
    Next
    INDEX
    Explanations

    explicit, direct

    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
     Essentially
    -0.08
     nahezu
    -0.08
    acher
    -0.07
     Seit
    -0.07
     люб
    -0.07
     willingly
    -0.07
    ćen
    -0.07
     prácticamente
    -0.07
    chin
    -0.07
    gema
    -0.07
    POSITIVE LOGITS
     copyrighted
    0.08
    ,但
    0.08
     saying
    0.08
    ніше
    0.08
     perfection
    0.08
     وراء
    0.08
    �
    0.08
    ú
    0.07
     तौर
    0.07
    ుడు
    0.07
    Activations Density 0.048%

    No Known Activations