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. 48952
    Prev
    Next
    INDEX
    Explanations

    r

    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
    weist
    -0.08
    magy
    -0.08
     KO
    -0.08
     ELSE
    -0.08
     Basically
    -0.08
     Nếu
    -0.08
    KEN
    -0.08
    itiro
    -0.08
     MMA
    -0.07
    랫
    -0.07
    POSITIVE LOGITS
    0.09
    0.08
    }_
    0.07
    �
    0.07
    �
    0.07
     dyn
    0.07
     conv
    0.07
    ය
    0.06
     attractiveness
    0.06
     වෙ
    0.06
    Activations Density 0.095%

    No Known Activations