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. 43061
    Prev
    Next
    INDEX
    Explanations

    thought

    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
     �
    -0.10
     правда
    -0.08
    ’t
    -0.08
    845
    -0.07
    �
    -0.07
    HW
    -0.07
     tasked
    -0.07
    സ
    -0.07
     пох
    -0.07
    pf
    -0.07
    POSITIVE LOGITS
    -provoking
    0.11
    itik
    0.08
    媒
    0.08
    fulness
    0.08
    ربة
    0.08
     무
    0.08
    akker
    0.07
    oen
    0.07
     saman
    0.07
     Mae
    0.07
    Activations Density 0.017%

    No Known Activations