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. 98292
    Prev
    Next
    INDEX
    Explanations

    infiltr

    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
    .exceptions
    -0.08
     exceptions
    -0.07
    angé
    -0.07
    cran
    -0.07
     instantaneous
    -0.07
    _coordinates
    -0.07
    _draw
    -0.07
    уді
    -0.07
    _runtime
    -0.07
    Exceptions
    -0.07
    POSITIVE LOGITS
     undercover
    0.15
     infiltr
    0.12
    欺
    0.10
     guise
    0.10
     infil
    0.10
     Fake
    0.10
     deception
    0.10
     infiltration
    0.10
     deceive
    0.09
     fake
    0.09
    Activations Density 0.047%

    No Known Activations