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. 41950
    Prev
    Next
    INDEX
    Explanations

    jump/to

    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
     biode
    -0.09
    oux
    -0.09
     ochr
    -0.09
    [:-
    -0.08
     undergoing
    -0.08
     ageing
    -0.08
     swords
    -0.08
    Outdoor
    -0.08
     delic
    -0.08
    rot
    -0.08
    POSITIVE LOGITS
    .jump
    0.14
     jump
    0.14
     jumps
    0.14
     Jump
    0.14
     jumped
    0.13
    Jump
    0.13
    _jump
    0.13
     jumping
    0.13
    jump
    0.12
    .goto
    0.12
    Activations Density 0.018%

    No Known Activations