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. 61060
    Prev
    Next
    INDEX
    Explanations

    breaking the fourth wall

    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
    Monto
    -0.09
    ترك
    -0.09
    Digest
    -0.08
    _digest
    -0.08
    itage
    -0.08
     tribut
    -0.08
     lider
    -0.08
     tungsten
    -0.08
     shortlist
    -0.08
     harp
    -0.08
    POSITIVE LOGITS
     glitches
    0.10
     glitch
    0.10
     reboot
    0.09
     BUG
    0.09
     RNG
    0.09
     plötzlich
    0.09
     hacker
    0.09
     rewind
    0.09
     simulation
    0.09
    剧情
    0.09
    Activations Density 0.092%

    No Known Activations