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. 59753
    Prev
    Next
    INDEX
    Explanations

    Jumping over something

    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
    .mult
    -0.08
    emu
    -0.08
    �
    -0.07
    .readlines
    -0.07
    Mult
    -0.07
    .default
    -0.07
     муль
    -0.07
     inducted
    -0.07
     exhibit
    -0.07
    .disable
    -0.07
    POSITIVE LOGITS
     déplacer
    0.10
     जाकर
    0.09
     แล
    0.09
     नए
    0.09
     менять
    0.09
    _swap
    0.09
     Jump
    0.08
    swap
    0.08
     прыг
    0.08
    plaatst
    0.08
    Activations Density 0.011%

    No Known Activations