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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 111903
    Prev
    Next
    INDEX
    Explanations

    lung

    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
     ordin
    -0.09
     bof
    -0.09
     wf
    -0.08
     Stub
    -0.08
     Galerie
    -0.08
    ീവ്
    -0.08
     göz
    -0.08
     Erick
    -0.08
     Etat
    -0.08
     Envelope
    -0.08
    POSITIVE LOGITS
     cancers
    0.13
     cancer
    0.11
     carcinoma
    0.10
     colorectal
    0.10
     cáncer
    0.09
     câncer
    0.09
    癌
    0.09
     tumors
    0.09
     melanoma
    0.08
    Dataset
    0.08
    Activations Density 0.010%

    No Known Activations