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. 15-RESID-POST-AA
    6. 19342
    Prev
    Next
    INDEX
    Explanations

    formal verification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    浆
    -0.10
     frappe
    -0.09
    okeh
    -0.09
    Panels
    -0.09
    _PANEL
    -0.09
     degust
    -0.09
     mysqli
    -0.08
     Rihanna
    -0.08
     poop
    -0.08
     marquee
    -0.08
    POSITIVE LOGITS
     proofs
    0.13
     FStar
    0.12
     guarantees
    0.12
     Isabelle
    0.12
     probabil
    0.12
     predicates
    0.12
     forall
    0.12
     correctness
    0.12
     certify
    0.12
     semantics
    0.12
    Activations Density 0.009%

    No Known Activations