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. 77511
    Prev
    Next
    INDEX
    Explanations

    D\&D game prompts

    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
     patent
    -0.09
    Patent
    -0.09
     wafer
    -0.08
     προηγ
    -0.08
    映
    -0.08
     cushion
    -0.08
    Bee
    -0.08
     moat
    -0.08
     amp
    -0.07
     convol
    -0.07
    POSITIVE LOGITS
     aventure
    0.09
     personaje
    0.09
     jugador
    0.09
    (player
    0.09
     joueur
    0.09
     jogador
    0.09
    [player
    0.09
     खिलाड़ी
    0.09
     Gothic
    0.09
     aventura
    0.09
    Activations Density 0.035%

    No Known Activations