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. 54296
    Prev
    Next
    INDEX
    Explanations

    Introducing an interesting point

    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
    Pai
    -0.08
    spoken
    -0.08
    HU
    -0.07
    uffy
    -0.07
    #a
    -0.07
     aerial
    -0.07
     spoken
    -0.07
     saura
    -0.07
    settings
    -0.07
    862
    -0.07
    POSITIVE LOGITS
    高潮
    0.10
     crucial
    0.09
     tricky
    0.09
     trouble
    0.09
     vaihe
    0.09
     entscheid
    0.08
    โช
    0.08
     चुनौती
    0.08
     단계
    0.08
     genius
    0.08
    Activations Density 0.036%

    No Known Activations