© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49676
    Prev
    Next
    INDEX
    Explanations

    Frame pointer/registers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eru
    -0.09
     inj
    -0.09
     erupted
    -0.08
    ૉ
    -0.08
    ,e
    -0.07
    ✓
    -0.07
    ʼe
    -0.07
     Latin
    -0.07
    dir
    -0.07
    @Request
    -0.07
    POSITIVE LOGITS
     FP
    0.11
     fp
    0.10
    FP
    0.10
     framebuffer
    0.10
    rw
    0.10
    fp
    0.10
    Framebuffer
    0.10
    RW
    0.09
    _FW
    0.09
     شاشة
    0.09
    Activations Density 0.001%

    No Known Activations