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. 23353
    Prev
    Next
    INDEX
    Explanations

    combining proteins

    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
    ിച്ചത്
    -0.08
     Jag
    -0.08
     sédu
    -0.07
    или
    -0.07
    Beauty
    -0.07
    Pear
    -0.07
    ിയ
    -0.07
     besides
    -0.07
     Jeg
    -0.07
     Yu
    -0.07
    POSITIVE LOGITS
    不用
    0.08
     обязательно
    0.08
     조금
    0.08
     pickle
    0.08
    ipta
    0.08
     జరిగ
    0.07
     TPU
    0.07
    lasses
    0.07
     Assembl
    0.07
    ctr
    0.07
    Activations Density 0.001%

    No Known Activations