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. 103977
    Prev
    Next
    INDEX
    Explanations

    lock

    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
     endors
    -0.08
    രു
    -0.08
    放心
    -0.08
     endorsed
    -0.08
    hea
    -0.08
    anaan
    -0.08
    (__
    -0.08
     frivol
    -0.08
     같은
    -0.08
    ു�
    -0.08
    POSITIVE LOGITS
     transitioning
    0.09
    Stepper
    0.08
     zonas
    0.08
     ચાર
    0.08
    383
    0.08
    Transitions
    0.08
    Transition
    0.08
     stepping
    0.08
    Resize
    0.08
     Transition
    0.08
    Activations Density 0.001%

    No Known Activations