© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 21507
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     identical
    -0.09
     rebel
    -0.08
     flawless
    -0.08
     diritto
    -0.08
     forced
    -0.08
     poslov
    -0.07
     rebellious
    -0.07
     failed
    -0.07
     flawed
    -0.07
    撤
    -0.07
    POSITIVE LOGITS
    范围
    0.25
     range
    0.25
     диапаз
    0.24
     ranges
    0.24
    _range
    0.23
    Range
    0.22
    range
    0.22
     Range
    0.22
    -range
    0.21
    _RANGE
    0.20
    Activations Density 0.022%

    No Known Activations