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. 76378
    Prev
    Next
    INDEX
    Explanations

    slot

    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
     Rab
    -0.08
     eb
    -0.08
    ة
    -0.07
     sür
    -0.07
     rikt
    -0.07
     bureau
    -0.07
     langer
    -0.07
     Arden
    -0.07
     вд
    -0.07
     হও
    -0.07
    POSITIVE LOGITS
    gor
    0.08
    guest
    0.08
     imb
    0.08
     Catherine
    0.08
     dig
    0.08
    dish
    0.08
     stag
    0.08
     wise
    0.08
     잡
    0.07
    mates
    0.07
    Activations Density 0.005%

    No Known Activations