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. 65799
    Prev
    Next
    INDEX
    Explanations

    franchise

    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
     pól
    -0.09
     tanks
    -0.08
     tacos
    -0.08
    孔
    -0.07
     tank
    -0.07
    壁
    -0.07
     plates
    -0.07
    筋
    -0.07
    拖
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     dita
    0.08
     shortened
    0.07
     Heath
    0.07
    ತ್ತು
    0.07
    ിയായി
    0.07
     ц
    0.07
    akad
    0.07
     October
    0.07
     expanded
    0.07
    play
    0.07
    Activations Density 0.003%

    No Known Activations