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. 24348
    Prev
    Next
    INDEX
    Explanations

    mathematical reflections

    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
     detaljer
    -0.09
     destinado
    -0.08
     élu
    -0.08
     narrowed
    -0.08
     claros
    -0.08
    уються
    -0.08
     overlooked
    -0.08
     Prä
    -0.08
     détails
    -0.08
     futurs
    -0.07
    POSITIVE LOGITS
     parity
    0.10
     Combined
    0.10
     togg
    0.09
     flips
    0.09
    flip
    0.09
    Parity
    0.09
     Twice
    0.08
    _flip
    0.08
     doubling
    0.08
     flipping
    0.08
    Activations Density 0.014%

    No Known Activations