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. 61306
    Prev
    Next
    INDEX
    Explanations

    releasing

    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
    -0.10
     будущем
    -0.09
     Zukunft
    -0.09
     futuro
    -0.09
     UNION
    -0.09
     avenir
    -0.08
     lixo
    -0.08
    _union
    -0.08
     frontier
    -0.08
     conferir
    -0.08
    POSITIVE LOGITS
     pounding
    0.10
     soaking
    0.09
    ressed
    0.08
     urge
    0.08
     clogged
    0.08
    -pressure
    0.08
    فاعل
    0.08
     pleading
    0.08
    Pressure
    0.08
     pressured
    0.08
    Activations Density 0.003%

    No Known Activations