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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102803
    Prev
    Next
    INDEX
    Explanations

    previous state

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *:
    -0.09
    Tours
    -0.08
     highlighted
    -0.08
    "]:
    -0.08
    *this
    -0.08
    üche
    -0.08
    _selected
    -0.08
    Selected
    -0.08
    _modified
    -0.08
    _des
    -0.07
    POSITIVE LOGITS
    prev
    0.14
     предыдущ
    0.14
    	prev
    0.13
     previous
    0.13
     અગાઉ
    0.13
     prev
    0.13
    (prev
    0.12
    previous
    0.12
     precedente
    0.12
     predecessor
    0.11
    Activations Density 0.000%

    No Known Activations