Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 131035
    Prev
    Next
    INDEX
    Explanations

    expense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simulator
    -0.08
    (sig
    -0.08
     sig
    -0.08
     Vernon
    -0.07
     Selena
    -0.07
    Fact
    -0.07
    เข้
    -0.07
     amps
    -0.07
     sel
    -0.07
     conception
    -0.07
    POSITIVE LOGITS
     sacrificing
    0.12
     sacrifice
    0.08
    �
    0.08
     نہیں
    0.08
     monopol
    0.08
     compromising
    0.08
     sacrifices
    0.08
     undes
    0.08
     dangerously
    0.08
     HTMLElement
    0.08
    Activations Density 0.019%

    No Known Activations