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. 102808
    Prev
    Next
    INDEX
    Explanations

    factor

    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
    .Objects
    -0.09
    geri
    -0.08
     Jack
    -0.07
    ovar
    -0.07
    ilos
    -0.07
     karta
    -0.07
    RET
    -0.07
     Mart
    -0.07
    areth
    -0.07
    tre
    -0.07
    POSITIVE LOGITS
     terbesar
    0.09
     pumpkin
    0.08
    :$
    0.08
    -leading
    0.08
    Explosion
    0.08
     speciale
    0.07
     vivendo
    0.07
     contagious
    0.07
    kach
    0.07
    �
    0.07
    Activations Density 0.001%

    No Known Activations