© 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. 22697
    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
    discussion
    -0.09
    nings
    -0.08
    ać
    -0.08
    يارات
    -0.08
     there's
    -0.08
    lisle
    -0.08
    cesz
    -0.08
    دڙ
    -0.08
    say
    -0.08
     اه
    -0.08
    POSITIVE LOGITS
     monarchy
    0.13
     positioning
    0.11
     noodzakelijk
    0.09
    -position
    0.09
    -zero
    0.09
    _position
    0.09
     certainty
    0.08
    _ZERO
    0.08
     positioned
    0.08
     Mehrheit
    0.08
    Activations Density 0.009%

    No Known Activations