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. 55999
    Prev
    Next
    INDEX
    Explanations

    �

    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
     Harrison
    -0.08
     Indep
    -0.08
     independ
    -0.08
     disconnected
    -0.08
    ACA
    -0.07
     unpar
    -0.07
    pets
    -0.07
     AC
    -0.07
    ေး
    -0.07
     recovering
    -0.07
    POSITIVE LOGITS
    Lemma
    0.09
    Pra
    0.08
    Proof
    0.08
     Arden
    0.08
    (cert
    0.08
     Lem
    0.08
     सिद्ध
    0.08
    ?id
    0.08
    Qed
    0.08
     prove
    0.08
    Activations Density 0.001%

    No Known Activations