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. 77124
    Prev
    Next
    INDEX
    Explanations

    NFA

    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
    Damage
    -0.09
     DAMAGE
    -0.08
    _DAMAGE
    -0.08
    _damage
    -0.08
     factions
    -0.08
     Damage
    -0.08
    enthal
    -0.08
     Britain
    -0.08
     faction
    -0.08
     Harm
    -0.08
    POSITIVE LOGITS
    ()]
    0.08
    -btn
    0.08
     possibil
    0.08
    Algorithm
    0.08
    算法
    0.08
    /antlr
    0.08
    automat
    0.08
     Algorithm
    0.08
    algorithm
    0.08
     algorithm
    0.08
    Activations Density 0.002%

    No Known Activations